|
|
|
|
| LEADER |
01000naa a22002652 4500 |
| 001 |
NLM327134011 |
| 003 |
DE-627 |
| 005 |
20231225200113.0 |
| 007 |
cr uuu---uuuuu |
| 008 |
231225s2021 xx |||||o 00| ||eng c |
| 024 |
7 |
|
|a 10.1109/TIP.2021.3089942
|2 doi
|
| 028 |
5 |
2 |
|a pubmed24n1090.xml
|
| 035 |
|
|
|a (DE-627)NLM327134011
|
| 035 |
|
|
|a (NLM)34166191
|
| 040 |
|
|
|a DE-627
|b ger
|c DE-627
|e rakwb
|
| 041 |
|
|
|a eng
|
| 100 |
1 |
|
|a Zhang, Chang-Bin
|e verfasserin
|4 aut
|
| 245 |
1 |
0 |
|a Delving Deep Into Label Smoothing
|
| 264 |
|
1 |
|c 2021
|
| 336 |
|
|
|a Text
|b txt
|2 rdacontent
|
| 337 |
|
|
|a ƒaComputermedien
|b c
|2 rdamedia
|
| 338 |
|
|
|a ƒa Online-Ressource
|b cr
|2 rdacarrier
|
| 500 |
|
|
|a Date Completed 30.09.2021
|
| 500 |
|
|
|a Date Revised 30.09.2021
|
| 500 |
|
|
|a published: Print-Electronic
|
| 500 |
|
|
|a Citation Status MEDLINE
|
| 520 |
|
|
|a Label smoothing is an effective regularization tool for deep neural networks (DNNs), which generates soft labels by applying a weighted average between the uniform distribution and the hard label. It is often used to reduce the overfitting problem of training DNNs and further improve classification performance. In this paper, we aim to investigate how to generate more reliable soft labels. We present an Online Label Smoothing (OLS) strategy, which generates soft labels based on the statistics of the model prediction for the target category. The proposed OLS constructs a more reasonable probability distribution between the target categories and non-target categories to supervise DNNs. Experiments demonstrate that based on the same classification models, the proposed approach can effectively improve the classification performance on CIFAR-100, ImageNet, and fine-grained datasets. Additionally, the proposed method can significantly improve the robustness of DNN models to noisy labels compared to current label smoothing approaches. The source code is available at our project page: https://mmcheng.net/ols/
|
| 650 |
|
4 |
|a Journal Article
|
| 700 |
1 |
|
|a Jiang, Peng-Tao
|e verfasserin
|4 aut
|
| 700 |
1 |
|
|a Hou, Qibin
|e verfasserin
|4 aut
|
| 700 |
1 |
|
|a Wei, Yunchao
|e verfasserin
|4 aut
|
| 700 |
1 |
|
|a Han, Qi
|e verfasserin
|4 aut
|
| 700 |
1 |
|
|a Li, Zhen
|e verfasserin
|4 aut
|
| 700 |
1 |
|
|a Cheng, Ming-Ming
|e verfasserin
|4 aut
|
| 773 |
0 |
8 |
|i Enthalten in
|t IEEE transactions on image processing : a publication of the IEEE Signal Processing Society
|d 1992
|g 30(2021) vom: 24., Seite 5984-5996
|w (DE-627)NLM09821456X
|x 1941-0042
|7 nnns
|
| 773 |
1 |
8 |
|g volume:30
|g year:2021
|g day:24
|g pages:5984-5996
|
| 856 |
4 |
0 |
|u http://dx.doi.org/10.1109/TIP.2021.3089942
|3 Volltext
|
| 912 |
|
|
|a GBV_USEFLAG_A
|
| 912 |
|
|
|a SYSFLAG_A
|
| 912 |
|
|
|a GBV_NLM
|
| 912 |
|
|
|a GBV_ILN_350
|
| 951 |
|
|
|a AR
|
| 952 |
|
|
|d 30
|j 2021
|b 24
|h 5984-5996
|